A community-college LMS tester mixes up “how the story is chopped,”…

Question

A community-college LMS tester mixes up “how the story is chopped,” “how each piece is numbered for meaning,” and “how much of the log still fits.” Which statement keeps the three LLM basics correctly separated?

Accepted Answer

Tokenization splits text into tokens; embeddings encode meaning as vectors; the context window limits how much prior text in tokens still fits — Chop the loaf, weigh each slice, then check how many slices fit in the toaster—three jobs, not one. Tokenization splits, embeddings encode meaning, and the context window caps prior text. Pasting test artefacts is easier when those three stay distinct.

Answer

Tokenization is the meaning vector; embeddings chop the story; the context window is another name for instruction tuning

Answer

Embeddings, tokenization, and context window are three labels for the same next-token prediction step

Answer

The context window creates embeddings; tokenization only applies to image models; embeddings set the window size

A community-college LMS tester mixes up “how the story is chopped,” “how each piece is numbered for meaning,” and “how much of the log still fits.” Which statement keeps the three LLM basics correctly separated?

Short Explanation

Full Explanation